Loading…
Loading…
Models / Bielik
2 models (11B to 11B) · ↓ 20.1K downloads a month · from $0.17/h on RTX 3090 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalspeakleash/Bielik-11B-v2.3-Instruct | vLLM | 22 GB | 28.9 GB | $0.21/h 2x RTX A4000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Bielik Minitron 7B v3.0 Instructspeakleash/Bielik-Minitron-7B-v3.0-InstructLicence to accept | vLLM | 15 GB | ~20.2 GB | $0.17/h RTX 3090 |
| Bielik 11B v3.0 Instructspeakleash/Bielik-11B-v3.0-InstructLicence to accept | vLLM | 22 GB | ~29 GB | $0.21/h 2x RTX A4000 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").